Admin-only crawler dashboard backed by an SSE live-status stream,
coordinated browser restart, runtime PHPSESSID refresh, dead-letter
requeue, and a batch of reliability fixes. Closes everything from
the two-pass audit (10 commits' worth) and bumps 0.52.0 -> 0.55.0.
Backend:
- New /admin/crawler/* surface (cookie-auth, RequireAdmin) split
into status / control / dead_jobs / backlog modules. SSE stream
composes in-memory status with DB-derived queue counts, memoizes
the counts for 1s and debounces watch pokes for 250ms (~10x QPS
reduction per subscriber). One-shot GET /admin/crawler shares the
same compose path.
- POST /admin/crawler/run gated by manual_pass_lock try_lock_owned
(409 Conflict on overlapping click); browser restart goes through
the coordinated_restart gate (drain + relaunch + auto-clear of the
sticky session_expired flag on Ok).
- Runtime PHPSESSID refresh via SessionController (allow-list
validation, never logged, audit row carries SHA-256 fingerprint).
Storage layer is repo::crawler::runtime_session_{load,persist}.
- Dead-letter requeue with four scopes (all/manga/chapter/job);
scope=all requires confirm:true; DISTINCT ON dedup keeps the
partial unique index from rejecting requeues for chapters with
multiple dead rows. SQL is four &'static str constants per scope.
- StatusHandle + ChapterGuard / CoverGuard RAII model survives
panics; last-writer-wins on cover so concurrent dispatches don't
clobber each other's slot. Pure functions (should_stop /
should_mark_clean_exit / should_abort_pass) with named regression
tests.
- Reliability bundle: per-lease heartbeat, jitter on retries,
per-job timeout, circuit breaker on consecutive failures, BrowserManager
coordinated restart gate, request fingerprint changes.
- Streaming page download: Storage::put_stream trait method,
LocalStorage impl atomic via temp + fsync + UUID-suffixed rename.
Pages stream through with peak memory ~one HTTP chunk + 64-byte
sniff prefix instead of one full image per dispatch.
- New partial indexes (migration 0022): mangas_missing_cover_idx
and crawler_jobs_dead_idx, both ordered by updated_at DESC to
match the dashboard's LIMIT/OFFSET reads.
- Security hardening: admin_csrf_guard (Origin/Referer allowlist
on /admin/* mutations, opt-in via ADMIN_ALLOWED_ORIGINS),
admin_no_store_guard (Cache-Control: no-store on admin
responses), audit rows carry per-scope target_id.
Frontend:
- /admin/crawler page decomposed into lib/components/crawler/
(11 components: ProgressBar, SearchBar, CrawlerHero,
CrawlerControls, ActiveChaptersCard, ActiveJobsTable,
MissingCoversTable, DeadJobsTable, RestartConfirmModal,
RequeueAllConfirmModal, SessionModal). Page is 532 LOC of
orchestration; each component 22-148 LOC.
- EventSource lifecycle wired to visibilitychange / pagehide /
pageshow (BFCache); after 5 consecutive errors probes the status
endpoint so a 401 routes through the global on401Hook instead of
infinite silent reconnects.
- Backlog $effect refetches debounced 500ms with per-loader
AbortControllers; refresh after a control action only runs when
the SSE stream is dead.
- Inline requeue button on /admin/mangas patches the affected row's
sync_state locally (no full chapter-list refetch); proper
aria-label. Requeue-all gets its own confirm modal; both confirm
modals autofocus Cancel.
- SvelteKit reverse proxy bypasses its 5-minute AbortController
for Accept: text/event-stream; pure shouldBypassProxyTimeout
helper covered by unit tests.
Config / docs:
- New env vars (.env.example): ADMIN_ALLOWED_ORIGINS,
CRAWLER_JOB_TIMEOUT_SECS, CRAWLER_METADATA_MAX_CONSECUTIVE_FAILURES,
CRAWLER_BROWSER_RESTART_THRESHOLD.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
229 lines
8.8 KiB
TypeScript
229 lines
8.8 KiB
TypeScript
import {
|
|
describe,
|
|
it,
|
|
expect,
|
|
vi,
|
|
beforeEach,
|
|
afterEach,
|
|
type MockInstance
|
|
} from 'vitest';
|
|
import { handle, shouldBypassProxyTimeout } from './hooks.server';
|
|
|
|
// `BACKEND_URL` is read at module load time, so the values used in the
|
|
// asserts below assume the test env didn't set it. `?? 'http://localhost:8080'`
|
|
// is the default.
|
|
const DEFAULT_BACKEND = 'http://localhost:8080';
|
|
|
|
function makeEvent(path: string, init?: RequestInit) {
|
|
const url = new URL(`http://app.example.com${path}`);
|
|
const request = new Request(url, init);
|
|
return { url, request } as Parameters<typeof handle>[0]['event'];
|
|
}
|
|
|
|
describe('hooks.server proxy', () => {
|
|
let fetchSpy: MockInstance<typeof globalThis.fetch>;
|
|
|
|
beforeEach(() => {
|
|
fetchSpy = vi.spyOn(globalThis, 'fetch');
|
|
});
|
|
afterEach(() => {
|
|
vi.restoreAllMocks();
|
|
});
|
|
|
|
it('forwards /api/* requests to the backend, preserving status', async () => {
|
|
fetchSpy.mockResolvedValueOnce(
|
|
new Response(JSON.stringify({ status: 'ok' }), {
|
|
status: 200,
|
|
headers: { 'content-type': 'application/json' }
|
|
})
|
|
);
|
|
const resolve = vi.fn();
|
|
|
|
const event = makeEvent('/api/v1/health');
|
|
const resp = await handle({ event, resolve });
|
|
|
|
expect(resolve).not.toHaveBeenCalled();
|
|
expect(fetchSpy).toHaveBeenCalledTimes(1);
|
|
expect(fetchSpy.mock.calls[0][0]).toBe(`${DEFAULT_BACKEND}/api/v1/health`);
|
|
expect(resp.status).toBe(200);
|
|
expect(await resp.json()).toEqual({ status: 'ok' });
|
|
});
|
|
|
|
it('passes through the query string', async () => {
|
|
fetchSpy.mockResolvedValueOnce(new Response('[]', { status: 200 }));
|
|
const resolve = vi.fn();
|
|
await handle({
|
|
event: makeEvent('/api/v1/mangas?search=narto&limit=10'),
|
|
resolve
|
|
});
|
|
expect(fetchSpy.mock.calls[0][0]).toBe(
|
|
`${DEFAULT_BACKEND}/api/v1/mangas?search=narto&limit=10`
|
|
);
|
|
});
|
|
|
|
it('strips the host header so the backend sees its own origin', async () => {
|
|
fetchSpy.mockResolvedValueOnce(new Response('[]', { status: 200 }));
|
|
const resolve = vi.fn();
|
|
await handle({
|
|
event: makeEvent('/api/v1/health', {
|
|
headers: { host: 'app.example.com', cookie: 'mangalord_session=abc' }
|
|
}),
|
|
resolve
|
|
});
|
|
const init = fetchSpy.mock.calls[0][1] as RequestInit;
|
|
const headers = init.headers as Headers;
|
|
expect(headers.get('host')).toBeNull();
|
|
// Cookies must still be forwarded — that's how the session reaches axum.
|
|
expect(headers.get('cookie')).toBe('mangalord_session=abc');
|
|
});
|
|
|
|
it('forwards request bodies on POST', async () => {
|
|
fetchSpy.mockResolvedValueOnce(new Response('{}', { status: 201 }));
|
|
const resolve = vi.fn();
|
|
await handle({
|
|
event: makeEvent('/api/v1/auth/login', {
|
|
method: 'POST',
|
|
headers: { 'content-type': 'application/json' },
|
|
body: JSON.stringify({ username: 'alice', password: 'hunter2hunter2' })
|
|
}),
|
|
resolve
|
|
});
|
|
const init = fetchSpy.mock.calls[0][1] as RequestInit;
|
|
expect(init.method).toBe('POST');
|
|
expect(init.body).toBeDefined();
|
|
});
|
|
|
|
it('delegates non-/api requests to SvelteKit', async () => {
|
|
const resolve = vi.fn().mockResolvedValue(new Response('page', { status: 200 }));
|
|
|
|
await handle({ event: makeEvent('/manga/abc'), resolve });
|
|
|
|
expect(fetchSpy).not.toHaveBeenCalled();
|
|
expect(resolve).toHaveBeenCalledTimes(1);
|
|
});
|
|
|
|
it('returns 502 with the standard error envelope when the upstream is unreachable', async () => {
|
|
// Silence the console.error the handler emits on failure so
|
|
// the test output stays clean.
|
|
const errSpy = vi.spyOn(console, 'error').mockImplementation(() => {});
|
|
fetchSpy.mockRejectedValueOnce(new TypeError('fetch failed'));
|
|
|
|
const resolve = vi.fn();
|
|
const resp = await handle({ event: makeEvent('/api/v1/health'), resolve });
|
|
|
|
expect(resolve).not.toHaveBeenCalled();
|
|
expect(resp.status).toBe(502);
|
|
expect(resp.headers.get('content-type')).toContain('application/json');
|
|
const body = await resp.json();
|
|
expect(body.error.code).toBe('upstream_unavailable');
|
|
expect(errSpy).toHaveBeenCalled();
|
|
});
|
|
|
|
it('strips every hop-by-hop header listed in RFC 7230 §6.1', async () => {
|
|
// Defence in depth: axum doesn't emit these, but a future
|
|
// middleware that did would otherwise leak per-connection
|
|
// state across the proxy boundary.
|
|
fetchSpy.mockResolvedValueOnce(new Response('[]', { status: 200 }));
|
|
const resolve = vi.fn();
|
|
await handle({
|
|
event: makeEvent('/api/v1/health', {
|
|
headers: {
|
|
host: 'app.example.com',
|
|
'content-length': '0',
|
|
connection: 'keep-alive',
|
|
'keep-alive': 'timeout=5',
|
|
'proxy-authenticate': 'Basic realm=x',
|
|
'proxy-authorization': 'Basic xyz',
|
|
te: 'trailers',
|
|
trailer: 'Expires',
|
|
'transfer-encoding': 'chunked',
|
|
upgrade: 'websocket',
|
|
// A non-hop-by-hop header to ensure non-targets
|
|
// aren't accidentally stripped.
|
|
'x-custom': 'pass-through'
|
|
}
|
|
}),
|
|
resolve
|
|
});
|
|
const init = fetchSpy.mock.calls[0][1] as RequestInit;
|
|
const headers = init.headers as Headers;
|
|
for (const h of [
|
|
'host',
|
|
'content-length',
|
|
'connection',
|
|
'keep-alive',
|
|
'proxy-authenticate',
|
|
'proxy-authorization',
|
|
'te',
|
|
'trailer',
|
|
'transfer-encoding',
|
|
'upgrade'
|
|
]) {
|
|
expect(headers.get(h), `${h} should be stripped`).toBeNull();
|
|
}
|
|
expect(headers.get('x-custom')).toBe('pass-through');
|
|
});
|
|
|
|
it('aborts and returns 502 when the upstream stalls past the timeout', async () => {
|
|
const errSpy = vi.spyOn(console, 'error').mockImplementation(() => {});
|
|
// Simulate an aborted fetch (AbortController.abort() raises a
|
|
// DOMException with name 'AbortError' on Node's fetch). The
|
|
// handler should treat it as the same upstream_unavailable
|
|
// 502 it uses for any other network failure.
|
|
const abortErr = new DOMException('aborted', 'AbortError');
|
|
fetchSpy.mockRejectedValueOnce(abortErr);
|
|
|
|
const resolve = vi.fn();
|
|
const resp = await handle({ event: makeEvent('/api/v1/slow'), resolve });
|
|
expect(resp.status).toBe(502);
|
|
const body = await resp.json();
|
|
expect(body.error.code).toBe('upstream_unavailable');
|
|
expect(errSpy).toHaveBeenCalled();
|
|
});
|
|
|
|
it('attaches an AbortSignal to the upstream fetch so it can time out', async () => {
|
|
fetchSpy.mockResolvedValueOnce(new Response('[]', { status: 200 }));
|
|
const resolve = vi.fn();
|
|
await handle({ event: makeEvent('/api/v1/health'), resolve });
|
|
const init = fetchSpy.mock.calls[0][1] as RequestInit;
|
|
expect(init.signal).toBeInstanceOf(AbortSignal);
|
|
// The signal hasn't fired (handler returned in time), but its
|
|
// presence is the contract this test is pinning.
|
|
expect(init.signal?.aborted).toBe(false);
|
|
});
|
|
});
|
|
|
|
// ----------------------------------------------------------------------------
|
|
// T1 — SSE bypass for the wall-clock proxy timeout.
|
|
// ----------------------------------------------------------------------------
|
|
|
|
describe('shouldBypassProxyTimeout', () => {
|
|
it('returns true for an SSE Accept header', () => {
|
|
const h = new Headers({ accept: 'text/event-stream' });
|
|
expect(shouldBypassProxyTimeout(h)).toBe(true);
|
|
});
|
|
|
|
it('matches case-insensitively', () => {
|
|
const h = new Headers({ accept: 'TEXT/EVENT-STREAM' });
|
|
expect(shouldBypassProxyTimeout(h)).toBe(true);
|
|
});
|
|
|
|
it('matches when SSE is one of several Accept values', () => {
|
|
const h = new Headers({ accept: 'text/event-stream, application/json' });
|
|
expect(shouldBypassProxyTimeout(h)).toBe(true);
|
|
});
|
|
|
|
it('returns false for plain JSON / HTML requests', () => {
|
|
expect(
|
|
shouldBypassProxyTimeout(new Headers({ accept: 'application/json' }))
|
|
).toBe(false);
|
|
expect(shouldBypassProxyTimeout(new Headers({ accept: 'text/html' }))).toBe(
|
|
false
|
|
);
|
|
});
|
|
|
|
it('returns false when Accept is absent', () => {
|
|
expect(shouldBypassProxyTimeout(new Headers())).toBe(false);
|
|
});
|
|
});
|